xoyeop's picture
Model save
1eed999 verified
metadata
license: mit
base_model: microsoft/deberta-v3-base
tags:
  - generated_from_trainer
metrics:
  - precision
  - recall
  - f1
  - accuracy
model-index:
  - name: deberta-v3-base-DIALOCONAN-WIKI-CLS
    results: []

deberta-v3-base-DIALOCONAN-WIKI-CLS

This model is a fine-tuned version of microsoft/deberta-v3-base on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 0.3828
  • Precision: 0.7060
  • Recall: 0.7086
  • F1: 0.7072
  • Accuracy: 0.9422

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

  • learning_rate: 3e-05
  • train_batch_size: 4
  • eval_batch_size: 4
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 5

Training results

Training Loss Epoch Step Validation Loss Precision Recall F1 Accuracy
0.4295 1.0 2500 0.5694 0.6816 0.6816 0.6793 0.9040
0.3525 2.0 5000 0.4852 0.6923 0.6938 0.6928 0.9225
0.2604 3.0 7500 0.4372 0.6993 0.7005 0.6995 0.9314
0.1979 4.0 10000 0.4076 0.7056 0.7077 0.7065 0.9410
0.1295 5.0 12500 0.3828 0.7060 0.7086 0.7072 0.9422

Framework versions

  • Transformers 4.42.4
  • Pytorch 2.3.1+cu121
  • Datasets 2.21.0
  • Tokenizers 0.19.1